GPT-6 Luna (Max) vs Inkling 2 Small
Which is better for the money: GPT-6 Luna (Max) by OpenAI or Inkling 2 Small by Thinking Machines? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-11-06.
Trade-off
Verdict
Depends on your budget
Inkling 2 Small scores 2.7 points higher (30.6 vs 27.9) but costs 5.8× as much to run the benchmark ($792 vs $136; premium vs mid-range cost classes). They are not alternatives at one budget: pick Inkling 2 Small when you need intelligence above 27.9, and GPT-6 Luna (Max) when 27.9 is enough.
| Metric | GPT-6 Luna (Max) | Inkling 2 Small | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 27.9 | 30.6 | +9.7% Inkling 2 Small is 9.7% more intelligent |
| Total AA cost (lower is better) | $136.06 | $791.81 | +482.0% Inkling 2 Small is 5.8× more expensive |
| End-to-end time (lower is better) | 126.31s | 20.92s | −83.4% Inkling 2 Small is 83.4% faster |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $0.30 / $1.00 | |
| Input modalities | Text, Image | Text, Image |
Inkling 2 Small vs GPT-6 Luna (Max): 9.7% more intelligence, 482.0% more cost to run the AA benchmark, and 83.4% faster end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-6 Luna (Max) is off the frontier: at the same or lower cost, Claude Haiku 5.5 (High) scores 29.90 for $121.
- Inkling 2 Small is off the frontier: at the same or lower cost, GPT-6.1 Sol (Xhigh) scores 52.50 for $718.
GPT-6 Luna (Max)Inkling 2 SmallToday's Pareto frontierEvery other model
Matchup
Compare something else
Agents:
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/gpt-6-luna/inkling-2-small · Markdown: /api/v1/compare/gpt-6-luna/inkling-2-small?format=md · llms.txt · agent skill